vl-download

videolectures.net video downloader
Version 0.1

README

@@ -0,0 +1,15 @@
+============================================
+		vl-download
+  		Version 0.1
+	videolectures.net video-download
+		Mayank Juneja
+	mayankjuneja1[AT]gmail[DOT]com
+============================================
+
+PREREQUISITES:
+  Python (>=2.7)  
+  BeautifulSoup,optparse (Python Modules)
+  rtmpdump (http://rtmpdump.mplayerhq.hu/)
+
+RUNNING
+  vl-download -u URL -o OUTFILE

vl-download

@@ -0,0 +1,87 @@
+#!/usr/bin/env python
+
+######################################################################
+#
+# vl-download.py : Download videos from videolectures.net
+# Author  : Mayank Juneja (mayankjuneja1[AT]gmail[DOT]com)
+# Version : 0.1
+#
+######################################################################
+
+
+import urllib2
+import re
+import os
+import sys
+from BeautifulSoup import BeautifulSoup
+from optparse      import OptionParser
+
+# Script Description
+desc = "videolectures.net video downloader"
+vers = "0.1"
+# Initialize Option Parser
+parser = OptionParser(description=desc,version = vers)
+
+# Add options
+
+parser.add_option("-u","--url",
+                dest="url",
+                help="videolecture.net URL",
+                metavar="URL")
+
+parser.add_option("-o","--outfile",
+                dest="outfile",
+                help="Output file Name",
+                metavar="outfile")
+
+
+# Parse arguments
+(options,args) = parser.parse_args()
+
+# Check for some mandatory Options
+if options.url is None:
+        # No URL specified
+        parser.error("--url option is required")
+
+        sys.exit(1)
+if options.outfile is None :
+        # Output file not specified
+        options.outfile = ""
+
+url = options.url
+outfile = options.outfile
+
+request_headers =  {
+        'User-Agent'		: 'User-Agent: Mozilla/5.0 (X11; Linux i686; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
+        'Accept'		: 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+        'Accept-Language'	: 'en-us,en;q=0.5',
+        'Accept-Charset'	: 'Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7',
+        'Keep-Alive'		: '300',
+        'Proxy-Connection'	: 'keep-alive',
+        'Cache-Control'		: 'max-age=0'
+       }
+
+
+req = urllib2.Request(url, None, request_headers)
+response = urllib2.urlopen(req)
+html_page = response.read()
+
+html_page = BeautifulSoup(html_page)
+
+## Find the metadata (Author, Title, Date)
+metadata = html_page.findAll(id='vl_desc')[0]
+title  = metadata.findAll('h2')[0].contents[0].encode('ascii','ignore')
+author = metadata.findAll("div",{"class":"lec_data"})[0].findAll("a")[0].contents[0].encode('ascii','ignore')
+
+## Find the rtmp data
+rtmp_section = html_page.findAll('script')[5].contents[0]
+rtmp_path = re.findall('clip.url.*\n',rtmp_section)[0].split("=")[1][2:-3]
+rtmp_url  = re.findall('clip.netConnectionUrl.*\n',rtmp_section)[0].split("=")[1][2:-3]
+
+## Begin downloading
+
+if(outfile==""):
+	outfile = author.replace(" ","_") + "-" + title.replace(" ","_")
+cmd = ("rtmpdump -r %s -y %s -o \"%s.flv\"")%(rtmp_url, rtmp_path, outfile)
+os.system(cmd)
+